AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams

Ziqiang Wang, Zhixiang Chi, Yanan Wu, Li Gu, Zhi Liu, Konstantinos N Plataniotis, Yang Wang

ECCV 2024 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
align test feature distributions to source statistics (DA loss) instead of entropy-based self-trainingTTA with BN affine layers · CIFAR10-C non-i.i.d.mean error (%): 27.6 (RoTTA) -> 24.3Improved
apply DA-TTA on CIFAR100-C non-i.i.d.TTA · CIFAR100-C non-i.i.d.mean error (%): 39.3 (MEMO) -> 31.6Improved
adapt with TTBN or entropy-based self-training under non-i.i.d. streamsTTBN, TENT, SAR, EATA, CoTTA · CIFAR10-C non-i.i.d.mean error (%): 43.5 (source) -> 75.7 (TTBN), 77.0 (TENT)Hurt
add entropy minimization loss on top of DA loss (ablation)DA-TTA · ImageNet-C non-i.i.d.mean error (%): 70.1 -> 64.8Improved
add entropy minimization loss on TTBN baseline (TENT) (ablation)TTBN · CIFAR10-C non-i.i.d.mean error (%): 75.7 -> 77.0Hurt
apply DA loss to all layers instead of only the latter half (ablation)DA-TTA · ImageNet-C non-i.i.d.mean error (%): 68.1 -> 64.8Improved
apply DA loss to all layers instead of only the former half (ablation)DA-TTA · CIFAR10-C non-i.i.d.mean error (%): 24.9 -> 24.3Improved
add domain shift detection with affine layer reset in continual TTADA-TTA · ImageNet-C continual non-i.i.d.mean error (%): 70.7 (LAME) -> 68.6; most competitors above 90% errorImproved
use DA-TTA on realistic domain shifts versus source modelDA-TTA · ImageNet-R non-i.i.d.error (%): 63.8 -> 58.5Improved
use DA-TTA on adversarial ImageNet-ADA-TTA · ImageNet-A non-i.i.d.error (%): 90.5 -> 88.6Improved
reduce batch size or increase label shift severity (ablation)existing TTA methods · non-i.i.d. streamserrorHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy